aishell例子，默认是linear的，我run_data和train都是mfcc，就出如下错误。难道是mfcc不能用吗？

----------- Configuration Arguments -----------
augment_conf_path: conf/augmentation.config
batch_size: 8
dev_manifest: data/aishell/manifest.dev
init_model_path: None
is_local: True
learning_rate: 5e-05
max_duration: 27.0
mean_std_path: data/aishell/mean_std.npz
min_duration: 0.0
num_conv_layers: 2
num_iter_print: 100
num_passes: 50
num_proc_data: 1
num_rnn_layers: 3
output_model_dir: ./checkpoints/aishell
rnn_layer_size: 1024
share_rnn_weights: False
shuffle_method: batch_shuffle_clipped
specgram_type: mfcc
test_off: False
train_manifest: data/aishell/manifest.train
trainer_count: 1
use_gpu: False
use_gru: True
use_sortagrad: True
vocab_path: data/aishell/vocab.txt
------------------------------------------------
I0325 10:29:09.558770 3291 Util.cpp:166] commandline: --use_gpu=False --rnn_use_batch=True --log_clipping=True --trainer_count=1
[INFO 2019-03-25 10:29:09,569 layers.py:2716] output for __conv_0__: c = 32, h = 81, w = 54, size = 139968
[INFO 2019-03-25 10:29:09,570 layers.py:3361] output for __batch_norm_0__: c = 32, h = 81, w = 54, size = 139968
[INFO 2019-03-25 10:29:09,571 layers.py:7533] output for __scale_sub_region_0__: c = 32, h = 81, w = 54, size = 139968
[INFO 2019-03-25 10:29:09,572 layers.py:2716] output for __conv_1__: c = 32, h = 41, w = 54, size = 70848
[INFO 2019-03-25 10:29:09,573 layers.py:3361] output for __batch_norm_1__: c = 32, h = 41, w = 54, size = 70848
[INFO 2019-03-25 10:29:09,574 layers.py:7533] output for __scale_sub_region_1__: c = 32, h = 41, w = 54, size = 70848
I0325 10:29:09.918823 3291 GradientMachine.cpp:94] Initing parameters..
I0325 10:29:12.502934 3291 GradientMachine.cpp:101] Init parameters done.
F0325 10:29:15.510699 3291 BlockExpandOp.cpp:73] Check failed: seqLength == outputHeight * outputWidth (47 vs. 18446744073709550206)
*** Check failure stack trace: ***
@ 0x7f5ee10e0ced google::LogMessage::Fail()
@ 0x7f5ee10e479c google::LogMessage::SendToLog()
@ 0x7f5ee10e0813 google::LogMessage::Flush()
@ 0x7f5ee10e5cae google::LogMessageFatal::~LogMessageFatal()
@ 0x7f5ee0f0cf36 paddle::BlockExpandFunction::getColShape()
@ 0x7f5ee0f0fa9a paddle::BlockExpandForward<>::calc()
@ 0x7f5ee0deafef paddle::BlockExpandLayer::forward()
@ 0x7f5ee0d6ea6d paddle::NeuralNetwork::forward()
@ 0x7f5ee0d6f6c3 paddle::GradientMachine::forwardBackward()
@ 0x7f5ee10bcca4 GradientMachine::forwardBackward()
@ 0x7f5ee0d07729 _wrap_GradientMachine_forwardBackward
@ 0x4c2e1e PyEval_EvalFrameEx
@ 0x4b9b66 PyEval_EvalCodeEx
@ 0x4c1f56 PyEval_EvalFrameEx
@ 0x4b9b66 PyEval_EvalCodeEx
@ 0x4c17c6 PyEval_EvalFrameEx
@ 0x4b9b66 PyEval_EvalCodeEx
@ 0x4c17c6 PyEval_EvalFrameEx
@ 0x4b9b66 PyEval_EvalCodeEx
@ 0x4c17c6 PyEval_EvalFrameEx
@ 0x4b9b66 PyEval_EvalCodeEx
@ 0x4c1f56 PyEval_EvalFrameEx
@ 0x4b9b66 PyEval_EvalCodeEx
@ 0x4c1f56 PyEval_EvalFrameEx
@ 0x4b9b66 PyEval_EvalCodeEx
@ 0x4eb69f (unknown)
@ 0x4e58f2 PyRun_FileExFlags
@ 0x54aae7 (unknown)
@ 0x4c1e1e PyEval_EvalFrameEx
@ 0x4b9b66 PyEval_EvalCodeEx
@ 0x4c17c6 PyEval_EvalFrameEx
@ 0x4c141f PyEval_EvalFrameEx

Process finished with exit code 134 (interrupted by signal 6: SIGABRT)